© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 45241
    Prev
    Next
    INDEX
    Explanations

    equivalence is isomorphic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çļĦéħįåIJĪ
    -0.07
    ersen
    -0.07
    æ¸ħæĺİ
    -0.07
    rodu
    -0.07
    éģ¿
    -0.06
    æ¸ħæ°Ķ
    -0.06
    çĻ¾èįī
    -0.06
    åĢļ
    -0.06
    å®īåħ¨éĺ²èĮĥ
    -0.06
    wick
    -0.06
    POSITIVE LOGITS
     equivalence
    0.11
    çĽ¸å·®
    0.11
    çĽ¸ä¼¼
    0.10
    çĽ¸ä¼¼çļĦ
    0.10
     similarity
    0.10
     nhau
    0.10
    åIJĮ声
    0.09
     similarities
    0.09
    ivalence
    0.09
    äºĴæį¢
    0.08
    Activations Density 0.024%

    No Known Activations